{
  "best_global_step": null,
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 3.0,
  "eval_steps": 100,
  "global_step": 96,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "entropy": 0.4654052224010229,
      "epoch": 0.32,
      "grad_norm": 0.048828125,
      "learning_rate": 6e-05,
      "loss": 0.30594801902770996,
      "mean_token_accuracy": 0.9038856193423271,
      "num_tokens": 460568.0,
      "step": 10
    },
    {
      "entropy": 0.42793196588754656,
      "epoch": 0.64,
      "grad_norm": 0.050537109375,
      "learning_rate": 6e-05,
      "loss": 0.2569255828857422,
      "mean_token_accuracy": 0.9156977899372578,
      "num_tokens": 916064.0,
      "step": 20
    },
    {
      "entropy": 0.41921926364302636,
      "epoch": 0.96,
      "grad_norm": 0.043701171875,
      "learning_rate": 6e-05,
      "loss": 0.26015210151672363,
      "mean_token_accuracy": 0.9139690645039081,
      "num_tokens": 1373088.0,
      "step": 30
    },
    {
      "entropy": 0.38780535757541656,
      "epoch": 1.256,
      "grad_norm": 0.042724609375,
      "learning_rate": 6e-05,
      "loss": 0.1978880524635315,
      "mean_token_accuracy": 0.9332824486332971,
      "num_tokens": 1799690.0,
      "step": 40
    },
    {
      "entropy": 0.3551080597564578,
      "epoch": 1.576,
      "grad_norm": 0.041259765625,
      "learning_rate": 6e-05,
      "loss": 0.18691558837890626,
      "mean_token_accuracy": 0.9357104673981667,
      "num_tokens": 2257096.0,
      "step": 50
    },
    {
      "entropy": 0.34900726228952406,
      "epoch": 1.896,
      "grad_norm": 0.042236328125,
      "learning_rate": 6e-05,
      "loss": 0.1920093059539795,
      "mean_token_accuracy": 0.9355965360999108,
      "num_tokens": 2710250.0,
      "step": 60
    },
    {
      "entropy": 0.32550016951722066,
      "epoch": 2.192,
      "grad_norm": 0.04443359375,
      "learning_rate": 6e-05,
      "loss": 0.16194652318954467,
      "mean_token_accuracy": 0.945790433400386,
      "num_tokens": 3126379.0,
      "step": 70
    },
    {
      "entropy": 0.2879067212343216,
      "epoch": 2.512,
      "grad_norm": 0.040771484375,
      "learning_rate": 6e-05,
      "loss": 0.14068626165390014,
      "mean_token_accuracy": 0.951568552851677,
      "num_tokens": 3590470.0,
      "step": 80
    },
    {
      "entropy": 0.27728699781000615,
      "epoch": 2.832,
      "grad_norm": 0.04052734375,
      "learning_rate": 6e-05,
      "loss": 0.134770405292511,
      "mean_token_accuracy": 0.9545286163687706,
      "num_tokens": 4047880.0,
      "step": 90
    },
    {
      "entropy": 0.29260293891032535,
      "epoch": 3.0,
      "mean_token_accuracy": 0.9474576853570484,
      "num_tokens": 4291239.0,
      "step": 96,
      "total_flos": 3.97466818052096e+16,
      "train_loss": 0.20133286652465662,
      "train_runtime": 225.298,
      "train_samples_per_second": 13.316,
      "train_steps_per_second": 0.426
    }
  ],
  "logging_steps": 10,
  "max_steps": 96,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 3,
  "save_steps": 100,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 3.97466818052096e+16,
  "train_batch_size": 1,
  "trial_name": null,
  "trial_params": null
}